Controlled Self-Evolution for Algorithmic Code Optimization Paper • 2601.07348 • Published 5 days ago • 104
KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions Paper • 2601.04745 • Published 9 days ago • 50
MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences Paper • 2601.06789 • Published 6 days ago • 73
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning Paper • 2601.06943 • Published 6 days ago • 201
GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts Paper • 2601.05110 • Published 8 days ago • 26
SWE-Exp: Experience-Driven Software Issue Resolution Paper • 2507.23361 • Published Jul 31, 2025 • 13
SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution Paper • 2507.23348 • Published Jul 31, 2025 • 11